CSF proteomics and machine learning reveal distinct stages across the Alzheimer’s disease continuum

Abstract Alzheimer’s disease (AD) is a neurodegenerative disorder characterized by heterogeneous pathophysiological changes that begin years before symptoms emerge. Existing biomarkers like Aβ and pTau capture only fragments of this complexity, limiting diagnosis and therapeutic development. Leveraging high-resolution cerebrospinal fluid (CSF) proteomics, quantifying 2,492 proteins using tandem-mass-tag mass spectrometry (TMT-MS), in 1,104 ADNI participants, we identified pathways reflecting AD pathogenesis and stage-specific molecular events in-vivo. In biomarker-positive MCI (due-to-AD) and AD Dementia, beyond well-established metabolic and mitochondrial dysfunction, we observed upregulated neuropeptide signaling, G-protein-coupled receptors activity, and synaptic remodeling, highlighting underrecognized synaptic and signaling alterations. Asymptomatic AD showed significant alterations in mitochondrial metabolism, RNA processing, and extracellular matrix pathways. Across the continuum from asymptomatic AD to MCI (due-to-AD) and AD Dementia, 92 proteins were differentially abundant, revealing a stage-specific progression, with early disruptions in neurodevelopmental and extracellular vesicle-related pathways in asymptomatic and MCI (due-to-AD) participants, transitioning to impairments in intracellular signaling, synaptic architecture, and cytoskeletal integrity in AD Dementia. This progressive dysregulation supports a continuum model where early compensatory mechanisms gradually give way to widespread neuronal degeneration. Using machine learning, we derived CSF proteomic panels capable of accurately distinguishing disease stages (asymptomatic AD vs. MCI (due-to-AD): AUC = 0.92; MCI (due-to-AD) vs. AD Dementia: AUC = 0.87). In parallel, we developed machine learning models to estimate pathological burden (Aβ-PET, tau-PET), which substantially outperformed conventional biomarkers. These findings uncover protein signatures that reflect underlying AD biology and provide a foundation for stage-specific biomarkers and therapeutic targeting, with important implications for patient stratification and personalized intervention strategies.

Authors

Institutions

Publication Details

Journal
Molecular Neurodegeneration
Published
2026-09-14
DOI
https://doi.org/10.1186/s13024-026-00983-9
Primary Topic
Alzheimer's disease research and treatments
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

CSF proteomics and machine learning reveal distinct stages across the Alzheimer’s disease continuum

Lawrence S. Honig, Clifford R. Jack, Marilyn Aiello, Karen L. Bell et al.
Molecular Neurodegeneration
Alzheimer's disease research and treatments
article

CSF proteomics and machine learning reveal distinct stages across the Alzheimer’s disease continuum

Lawrence S. Honig, Clifford R. Jack, Marilyn Aiello, Karen L. Bell, Arthur W. Toga, Raj C. Shah, Judith L. Heidebrink, Peggy Roberts, Henry Rusinek, John Kornak, Randall Griffith, Heather S. Anderson, Sonia Pawluczyk, Helen Vanderswag, Joanne Lord, Adrian Preda, Daniel Silverman, Ronald G. Thomas, Steven G. Potkin, Javier Villanueva‐Meyer, Julia Pedroso, Eric B. Dammer, John C. Morris, Sara Dolen, Daniel Varón, Susan M De Santi, Stacy Schneider, George Bartzokis, Anantharaman Shantaraman, Mark A. Mintun, Scott Herring, Connie Brand, Ranjan Duara, Mony J. de Leon, Oscar L. López, Edward J. Fox, Fang Wu, Saima Rathore, Duc M. Duong, Paul Thompson, Janet S. Cellar, Po H. Lu, Daniel Marson, Catherine Mc-Adams-Ortiz, Donna M. Simpson, Ruth A. Mulnard, Leyla deToledo‐Morrell, Marilyn Albert, Erik C B Johnson, Kris Johnson, Rachelle S. Doody, Charles D. Smith, Peter Hardy, Dana Nguyen, Joseph Quinn, Curtis A. Given, Gaby Thai, Munir Chowdhury, Jeffrey R. Petrella, Norbert Schuff, Bryan M. Spann, Anthony Gamst, Owen Carmichael, Jaimie Toroney, Ann M. Hake, Andrew J. Saykin, MaryAnn Oakley, Michael Donohue, Alzheimer’s Disease Neuroimaging Initiative, Sarah Walter, Charles DeCarli, Lon Schneider, James Brewer, M. Saleem Ismail, Laurel Beckett, Ronald Petersen, Danielle Harvey, Martin Farlow, Anders Dale, James J. Lah, Yaakov Stern, Neil Buckholtz, Matthew Bernstein, David Clark, Joel Felmlee, Evan Fletcher, Karen Crawford, Jeffrey Kaye, Paul Aisen, George Marzloff, Tatiana M. Foroud, Cheuk Tang, Jennifer Richard, Li Shen, P. Murali Doraiswamy, Jeffrey M. Burns, Hillel Grossman, Allan I. Levey, Scott Neu
article en

Abstract

Abstract Alzheimer’s disease (AD) is a neurodegenerative disorder characterized by heterogeneous pathophysiological changes that begin years before symptoms emerge. Existing biomarkers like Aβ and pTau capture only fragments of this complexity, limiting diagnosis and therapeutic development. Leveraging high-resolution cerebrospinal fluid (CSF) proteomics, quantifying 2,492 proteins using tandem-mass-tag mass spectrometry (TMT-MS), in 1,104 ADNI participants, we identified pathways reflecting AD pathogenesis and stage-specific molecular events in-vivo. In biomarker-positive MCI (due-to-AD) and AD Dementia, beyond well-established metabolic and mitochondrial dysfunction, we observed upregulated neuropeptide signaling, G-protein-coupled receptors activity, and synaptic remodeling, highlighting underrecognized synaptic and signaling alterations. Asymptomatic AD showed significant alterations in mitochondrial metabolism, RNA processing, and extracellular matrix pathways. Across the continuum from asymptomatic AD to MCI (due-to-AD) and AD Dementia, 92 proteins were differentially abundant, revealing a stage-specific progression, with early disruptions in neurodevelopmental and extracellular vesicle-related pathways in asymptomatic and MCI (due-to-AD) participants, transitioning to impairments in intracellular signaling, synaptic architecture, and cytoskeletal integrity in AD Dementia. This progressive dysregulation supports a continuum model where early compensatory mechanisms gradually give way to widespread neuronal degeneration. Using machine learning, we derived CSF proteomic panels capable of accurately distinguishing disease stages (asymptomatic AD vs. MCI (due-to-AD): AUC = 0.92; MCI (due-to-AD) vs. AD Dementia: AUC = 0.87). In parallel, we developed machine learning models to estimate pathological burden (Aβ-PET, tau-PET), which substantially outperformed conventional biomarkers. These findings uncover protein signatures that reflect underlying AD biology and provide a foundation for stage-specific biomarkers and therapeutic targeting, with important implications for patient stratification and personalized intervention strategies.

Molecular Neurodegeneration
Emory University (US)
Openalex Percentile: Top 11%
Alzheimer's disease research and treatments
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.